Best models for this Mac

29 modelsCatalog current through February 27, 2026

Mac Studio M4 Max 128GB ranked for coding with a most capable bias, using the best available runtime evidence.

Mac

Capability

Bias

Runtime

Use the strongest current runtime evidence for each row.M5 Max watch: 8B 61.6 tok/s · 14B 34.3 tok/s on the current 36GB public anchor.

Rank	Model	Score	Quant	Tok/s	Runtime	Evidence	Headroom	Why it ranks here
1	Qwen3.5-27B	264	8bit	20.6 tok/s	MLX	Estimated	100.4 GB	8bit is the highest practical quality here. 20.6 tok/s estimated from nearby benchmark coverage, with MLX backend as the best runtime hint. 100.4 GB headroom leaves workable context margin.
2	Qwen 3 32B	264	8bit	11.7 tok/s	LM Studio	Estimated	95.0 GB	8bit is the highest practical quality here. 11.7 tok/s estimated from nearby benchmark coverage, with LM Studio wrapper on mixed as the best runtime hint. 95.0 GB headroom leaves workable context margin.
3	Devstral Small 1.1	262	8bit	33.0 tok/s	LM Studio	Estimated	103.9 GB	8bit is the highest practical quality here. 33.0 tok/s estimated from nearby benchmark coverage, with LM Studio wrapper on mixed as the best runtime hint. 103.9 GB headroom leaves workable context margin.
4	Devstral Small 2 24B	262	8bit	25.3 tok/s	MLX	Estimated	103.9 GB	8bit is the highest practical quality here. 25.3 tok/s estimated from nearby benchmark coverage, with MLX backend as the best runtime hint. 103.9 GB headroom leaves workable context margin.
5	Gemma 3 27B	259	8bit	14.5 tok/s	LM Studio	Estimated	98.1 GB	8bit is the highest practical quality here. 14.5 tok/s estimated from nearby benchmark coverage, with LM Studio wrapper on mixed as the best runtime hint. 98.1 GB headroom leaves workable context margin.
6	Llama 3.3 70B	255	8bit	6.5 tok/s	LM Studio	Measured	59.2 GB	8bit is the highest practical quality here. 6.5 tok/s measured on LM Studio wrapper on mixed. 59.2 GB headroom leaves workable context margin.
7	DeepSeek R1 Distill Qwen 32B	252	8bit	Measure it	Best available	Fit-first	95.0 GB	8bit is the highest practical quality here. Speed still needs direct measurement. 95.0 GB headroom leaves workable context margin.
8	Mistral Small 3.1 24B	240	8bit	Measure it	Best available	Fit-first	103.9 GB	8bit is the highest practical quality here. Speed still needs direct measurement. 103.9 GB headroom leaves workable context margin.
9	Magistral Small	240	8bit	Measure it	Best available	Fit-first	103.9 GB	8bit is the highest practical quality here. Speed still needs direct measurement. 103.9 GB headroom leaves workable context margin.
10	Nemotron-3-Nano-30B-A3B	233	8bit	43.7 tok/s	llama.cpp	Estimated	99.2 GB	8bit is the highest practical quality here. 43.7 tok/s estimated from nearby benchmark coverage, with llama.cpp backend as the best runtime hint. 99.2 GB headroom leaves workable context margin.
11	Qwen 3 30B-A3B	233	8bit	70.2 tok/s	LM Studio	Estimated	98.3 GB	8bit is the highest practical quality here. 70.2 tok/s estimated from nearby benchmark coverage, with LM Studio wrapper on mixed as the best runtime hint. 98.3 GB headroom leaves workable context margin.
12	Qwen3-Coder-30B-A3B	233	8bit	58.5 tok/s	llama.cpp	Estimated	98.7 GB	8bit is the highest practical quality here. 58.5 tok/s estimated from nearby benchmark coverage, with llama.cpp backend as the best runtime hint. 98.7 GB headroom leaves workable context margin.
13	Qwen3.5-35B-A3B	232	8bit	80.0 tok/s	MLX	Estimated	94.3 GB	8bit is the highest practical quality here. 80.0 tok/s estimated from nearby benchmark coverage, with MLX backend as the best runtime hint. 94.3 GB headroom leaves workable context margin.
14	GLM-4.7-Flash	232	8bit	36.8 tok/s	llama.cpp	Estimated	92.2 GB	8bit is the highest practical quality here. 36.8 tok/s estimated from nearby benchmark coverage, with llama.cpp backend as the best runtime hint. 92.2 GB headroom leaves workable context margin.
15	Qwen 3 8B	211	8bit	63.1 tok/s	LM Studio	Estimated	118.7 GB	8bit is the highest practical quality here. 63.1 tok/s estimated from nearby benchmark coverage, with LM Studio wrapper on mixed as the best runtime hint. 118.7 GB headroom leaves workable context margin.
16	Llama 2 7B	209	8bit	36.4 tok/s	llama.cpp	Estimated	117.2 GB	8bit is the highest practical quality here. 36.4 tok/s estimated from nearby benchmark coverage, with llama.cpp backend as the best runtime hint. 117.2 GB headroom leaves workable context margin.
17	Qwen3.5-9B	206	8bit	15.0 tok/s	llama.cpp	Estimated	118.1 GB	8bit is the highest practical quality here. 15.0 tok/s estimated from nearby benchmark coverage, with llama.cpp backend as the best runtime hint. 118.1 GB headroom leaves workable context margin.
18	Qwen 2.5 14B	199	8bit	Measure it	Best available	Fit-first	113.0 GB	8bit is the highest practical quality here. Speed still needs direct measurement. 113.0 GB headroom leaves workable context margin.
19	Phi-4 14B	198	8bit	Measure it	Best available	Fit-first	113.5 GB	8bit is the highest practical quality here. Speed still needs direct measurement. 113.5 GB headroom leaves workable context margin.
20	Llama 3.1 8B	189	8bit	Measure it	Best available	Fit-first	119.0 GB	8bit is the highest practical quality here. Speed still needs direct measurement. 119.0 GB headroom leaves workable context margin.
21	GLM-4.5-Air	189	8bit	54.0 tok/s	MLX	Estimated	27.3 GB	8bit is the highest practical quality here. 54.0 tok/s estimated from nearby benchmark coverage, with MLX backend as the best runtime hint. 27.3 GB headroom leaves workable context margin.
22	Qwen 2.5 7B	189	8bit	Measure it	Best available	Fit-first	120.0 GB	8bit is the highest practical quality here. Speed still needs direct measurement. 120.0 GB headroom leaves workable context margin.
23	Mistral 7B v0.3	188	8bit	Measure it	Best available	Fit-first	119.7 GB	8bit is the highest practical quality here. Speed still needs direct measurement. 119.7 GB headroom leaves workable context margin.
24	Qwen3.5-122B-A10B	180	Q6_K	57.0 tok/s	MLX	Estimated	33.6 GB	Q6_K is the highest practical quality here. 57.0 tok/s estimated from nearby benchmark coverage, with MLX backend as the best runtime hint. 33.6 GB headroom leaves workable context margin.
25	Qwen3-Coder-Next	176	8bit	74.0 tok/s	MLX	Estimated	52.2 GB	8bit is the highest practical quality here. 74.0 tok/s estimated from nearby benchmark coverage, with MLX backend as the best runtime hint. 52.2 GB headroom leaves workable context margin.
26	Gemma 3 4B	150	8bit	100.5 tok/s	LM Studio	Estimated	122.4 GB	8bit is the highest practical quality here. 100.5 tok/s estimated from nearby benchmark coverage, with LM Studio wrapper on mixed as the best runtime hint. 122.4 GB headroom leaves workable context margin.
27	Qwen 3 4B	150	8bit	143.2 tok/s	MLX	Estimated	122.6 GB	8bit is the highest practical quality here. 143.2 tok/s estimated from nearby benchmark coverage, with MLX backend as the best runtime hint. 122.6 GB headroom leaves workable context margin.
28	Qwen 3 0.6B	145	8bit	184.4 tok/s	LM Studio	Estimated	126.8 GB	8bit is the highest practical quality here. 184.4 tok/s estimated from nearby benchmark coverage, with LM Studio wrapper on mixed as the best runtime hint. 126.8 GB headroom leaves workable context margin.
29	Llama 3.2 1B	124	8bit	Measure it	Best available	Fit-first	126.1 GB	8bit is the highest practical quality here. Speed still needs direct measurement. 126.1 GB headroom leaves workable context margin.

Machine

128GBUnified memory

$4,499MSRP

mac_studioForm factor

m4-maxChip